def init_one_meta(self, seed):
cps = generate_categories_profiles(self.categories)
if not self.duplication and self.renewal_method > 0:
for crit in self.criteria.values():
if int(crit.id[1:]) <= self.nb_unk_criteria:
tmp = random.random()
if tmp < 0.5:
crit.direction = -1
else:
crit.direction = 1
#print(tmp)
#print(self.unk_pref_dir_criteria,int(crit.id[1:]),self.criteria)
#import pdb; pdb.set_trace()
#print(self.criteria,self.renewal_method)
#import pdb; pdb.set_trace()
model = MRSort(copy.deepcopy(self.criteria), None, None, None, cps)
model.id = 'model_%d' % seed
meta = MetaMRSortCV4MSJP(model,
self.pt_sorted,
self.aa_ori,
self.lp_weights,
self.heur_profiles,
self.lp_veto_weights,
self.heur_veto_profiles,
gamma=self.gamma,
renewal_method=self.renewal_method,
pretreatment_crit=self.pretreatment_crit,
duplication=self.duplication,
nb_unk_criteria=self.nb_unk_criteria)
random.seed(seed)
meta.random_state = random.getstate()
meta.auc = meta.model.auc(self.aa_ori, self.pt_sorted.pt)
return meta
def init_one_meta(self, seed):
cps = generate_categories_profiles(self.categories)
model = MRSort(self.criteria, None, None, None, cps)
model.id = 'model_%d' % seed
meta = MetaMRSortCV4(model, self.pt_sorted, self.aa_ori,
self.lp_weights, self.heur_profiles,
self.lp_veto_weights, self.heur_veto_profiles)
random.seed(seed)
meta.random_state = random.getstate()
meta.auc = meta.model.auc(self.aa_ori, self.pt_sorted.pt)
return meta
def init_one_meta(self, seed):
cps = generate_categories_profiles(self.categories)
model = MRSort(self.criteria, None, None, None, cps)
model.id = 'model_%d' % seed
meta = MetaMRSortCV4(model, self.pt_sorted, self.aa_ori,
self.lp_weights,
self.heur_profiles,
self.lp_veto_weights,
self.heur_veto_profiles)
random.seed(seed)
meta.random_state = random.getstate()
meta.auc = meta.model.auc(self.aa_ori, self.pt_sorted.pt)
return meta
def test_meta_electre_tri_global(seed, na, nc, ncat, na_gen, pcerrors):
# Generate a random ELECTRE TRI BM model
if random_model_type == 'default':
model = generate_random_mrsort_model(nc, ncat, seed)
elif random_model_type == 'choquet':
model = generate_random_mrsort_choquet_model(nc, ncat, 2, seed)
# Generate a set of alternatives
a = generate_alternatives(na)
pt = generate_random_performance_table(a, model.criteria)
aa = model.pessimist(pt)
# Add errors in assignment examples
aa_err = aa.copy()
aa_erroned = add_errors_in_assignments_proba(aa_err, model.categories,
pcerrors / 100)
na_err = len(aa_erroned)
# Run the MIP
t1 = time.time()
model2 = MRSort(model.criteria, None, None, None,
model.categories_profiles, None, None, None)
mip = MipMRSort(model2, pt, aa_err)
obj = mip.solve()
ca2_best = obj / na
aa2 = model2.get_assignments(pt)
t_total = time.time() - t1
# Determine the number of erroned alternatives badly assigned
aa2 = model2.pessimist(pt)
ok_errors = ok2_errors = ok = 0
for alt in a:
if aa(alt.id) == aa2(alt.id):
if alt.id in aa_erroned:
ok_errors += 1
ok += 1
if aa_err(alt.id) == aa2(alt.id) and alt.id in aa_erroned:
ok2_errors += 1
total = len(a)
ca2_errors = ok2_errors / total
ca_best = ok / total
ca_errors = ok_errors / total
# Generate alternatives for the generalization
a_gen = generate_alternatives(na_gen)
pt_gen = generate_random_performance_table(a_gen, model.criteria)
aa_gen = model.pessimist(pt_gen)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen = compute_ca(aa_gen, aa_gen2)
aa_gen_err = aa_gen.copy()
aa_gen_erroned = add_errors_in_assignments_proba(aa_gen_err,
model.categories,
pcerrors / 100)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen_err = compute_ca(aa_gen_err, aa_gen2)
# Save all infos in test_result class
t = test_result("%s-%d-%d-%d-%d-%g" %
(seed, na, nc, ncat, na_gen, pcerrors))
model.id = 'initial'
model2.id = 'learned'
pt.id, pt_gen.id = 'learning_set', 'test_set'
aa.id = 'aa'
aa_err.id = 'aa_err'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name), model, model2, pt,
pt_gen, aa, aa_err)
# Input params
t['seed'] = seed
t['na'] = na
t['nc'] = nc
t['ncat'] = ncat
t['na_gen'] = na_gen
t['pcerrors'] = pcerrors
# Ouput params
t['na_err'] = na_err
t['ca_best'] = ca_best
t['ca_errors'] = ca_errors
t['ca2_best'] = ca2_best
t['ca2_errors'] = ca2_errors
t['ca_gen'] = ca_gen
t['ca_gen_err'] = ca_gen_err
t['t_total'] = t_total
return t
def test_mip_mrsort_vc(seed, na, nc, ncat, na_gen, veto_param, pcerrors):
# Generate a random ELECTRE TRI BM model
if vetot == 'binary':
model = generate_random_mrsort_model_with_binary_veto(nc, ncat,
seed,
veto_func = veto_func,
veto_param = veto_param)
elif vetot == 'coalition':
model = generate_random_mrsort_model_with_coalition_veto(nc, ncat,
seed,
veto_weights = indep_veto_weights,
veto_func = veto_func,
veto_param = veto_param)
# Generate a set of alternatives
a = generate_alternatives(na)
pt = generate_random_performance_table(a, model.criteria)
aa = model.pessimist(pt)
nv_m1_learning = sum([model.count_veto_pessimist(ap) for ap in pt])
# Add errors in assignment examples
aa_err = aa.copy()
aa_erroned = add_errors_in_assignments_proba(aa_err,
model.categories,
pcerrors / 100)
na_err = len(aa_erroned)
# Run the MIP
t1 = time.time()
model2 = MRSort(model.criteria, None, None, None,
model.categories_profiles, None, None, None)
if algo == MipMRSortVC and vetot == 'binary':
w = {c.id: 1 / len(model.criteria) for c in model.criteria}
w1 = w.keys()[0]
w[w1] += 1 - sum(w.values())
model2.veto_weights = CriteriaValues([CriterionValue(c.id,
w[c.id])
for c in model.criteria])
model2.veto_lbda = min(w.values())
if algo == MipMRSortVC:
mip = MipMRSortVC(model2, pt, aa, indep_veto_weights)
else:
mip = MipMRSort(model2, pt, aa)
mip.solve()
t_total = time.time() - t1
# Determine the number of erroned alternatives badly assigned
aa2 = model2.pessimist(pt)
nv_m2_learning = sum([model2.count_veto_pessimist(ap) for ap in pt])
cmatrix_learning = compute_confusion_matrix(aa, aa2, model.categories)
ok_errors = ok2_errors = ok = 0
for alt in a:
if aa(alt.id) == aa2(alt.id):
if alt.id in aa_erroned:
ok_errors += 1
ok += 1
if aa_err(alt.id) == aa2(alt.id) and alt.id in aa_erroned:
ok2_errors += 1
total = len(a)
ca2_errors = ok2_errors / total
ca_best = ok / total
ca_errors = ok_errors / total
# Generate alternatives for the generalization
a_gen = generate_alternatives(na_gen)
pt_gen = generate_random_performance_table(a_gen, model.criteria)
aa_gen = model.pessimist(pt_gen)
aa_gen2 = model2.pessimist(pt_gen)
nv_m1_gen = sum([model.count_veto_pessimist(ap) for ap in pt_gen])
nv_m2_gen = sum([model2.count_veto_pessimist(ap) for ap in pt_gen])
if len(aa_gen) > 0:
cmatrix_gen = compute_confusion_matrix(aa_gen, aa_gen2,
model.categories)
ca_gen = compute_ca(aa_gen, aa_gen2)
aa_gen_err = aa_gen.copy()
aa_gen_erroned = add_errors_in_assignments_proba(aa_gen_err,
model.categories,
pcerrors / 100)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen_err = compute_ca(aa_gen_err, aa_gen2)
# Save all infos in test_result class
t = test_result("%s-%d-%d-%d-%d-%s-%d" % (seed, na, nc, ncat,
na_gen, veto_param, pcerrors))
model.id = 'initial'
model2.id = 'learned'
a.id, pt.id = 'learning_set', 'learning_set'
aa.id, aa2.id = 'learning_set_m1', 'learning_set_m2'
a_gen.id, pt_gen.id = 'test_set', 'test_set'
aa_gen.id, aa_gen2.id = 'test_set_m1', 'test_set_m2'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name),
model, model2, a, a_gen, pt, pt_gen, aa, aa2,
aa_gen, aa_gen2)
# Input params
t['seed'] = seed
t['na'] = na
t['nc'] = nc
t['ncat'] = ncat
t['na_gen'] = na_gen
t['veto_param'] = veto_param
t['pcerrors'] = pcerrors
# Ouput params
t['na_err'] = na_err
t['nv_m1_learning'] = nv_m1_learning
t['nv_m2_learning'] = nv_m2_learning
t['nv_m1_gen'] = nv_m1_gen
t['nv_m2_gen'] = nv_m2_gen
t['ca_best'] = ca_best
t['ca_errors'] = ca_errors
t['ca_gen'] = ca_gen
t['ca_gen_err'] = ca_gen_err
t['t_total'] = t_total
for k, v in cmatrix_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in cmatrix_gen.items():
t['test_%s_%s' % (k[0], k[1])] = v
return t
def run_test(seed, data, pclearning):
random.seed(seed)
# Separate learning data and test data
pt_learning, pt_test = data.pt.split(2, [pclearning, 100 - pclearning])
aa_learning = data.aa.get_subset(pt_learning.keys())
aa_test = data.aa.get_subset(pt_test.keys())
# Initialize ELECTRE-TRI BM model
cat_profiles = generate_categories_profiles(data.cats)
worst = data.pt.get_worst(data.c)
best = data.pt.get_best(data.c)
b = generate_alternatives(len(data.cats) - 1, 'b')
bpt = None
cvs = None
lbda = None
model = MRSort(data.c, cvs, bpt, lbda, cat_profiles)
# Run the linear program
t1 = time.time()
mip = mip_mrsort(model, pt_learning, aa_learning)
obj = mip.solve()
t_total = time.time() - t1
# CA learning set
aa_learning2 = model.pessimist(pt_learning)
ca_learning = compute_ca(aa_learning, aa_learning2)
auc_learning = model.auc(aa_learning, pt_learning)
diff_learning = compute_confusion_matrix(aa_learning, aa_learning2,
model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2 = model.pessimist(pt_test)
ca_test = compute_ca(aa_test, aa_test2)
auc_test = model.auc(aa_test, pt_test)
diff_test = compute_confusion_matrix(aa_test, aa_test2,
model.categories)
else:
ca_test = 0
auc_test = 0
ncat = len(data.cats)
diff_test = OrderedDict([((a, b), 0) for a in model.categories \
for b in model.categories])
# Compute CA of whole set
aa2 = model.pessimist(data.pt)
ca = compute_ca(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
diff_all = compute_confusion_matrix(data.aa, aa2, model.categories)
t = test_result("%s-%d-%d" % (data.name, seed, pclearning))
model.id = 'learned'
aa_learning.id, aa_test.id = 'learning_set', 'test_set'
pt_learning.id, pt_test.id = 'learning_set', 'test_set'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name), model, aa_learning,
aa_test, pt_learning, pt_test)
t['seed'] = seed
t['na'] = len(data.a)
t['nc'] = len(data.c)
t['ncat'] = len(data.cats)
t['pclearning'] = pclearning
t['na_learning'] = len(aa_learning)
t['na_test'] = len(aa_test)
t['obj'] = obj
t['ca_learning'] = ca_learning
t['ca_test'] = ca_test
t['ca_all'] = ca
t['auc_learning'] = auc_learning
t['auc_test'] = auc_test
t['auc_all'] = auc
for k, v in diff_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in diff_test.items():
t['test_%s_%s' % (k[0], k[1])] = v
for k, v in diff_all.items():
t['all_%s_%s' % (k[0], k[1])] = v
t['t_total'] = t_total
return t
def test_meta_electre_tri_global(seed, na, nc, ncat, na_gen, pcerrors):
# Generate a random ELECTRE TRI BM model
if random_model_type == 'default':
model = generate_random_mrsort_model(nc, ncat, seed)
elif random_model_type == 'choquet':
model = generate_random_mrsort_choquet_model(nc, ncat, 2, seed)
# Generate a set of alternatives
a = generate_alternatives(na)
pt = generate_random_performance_table(a, model.criteria)
aa = model.pessimist(pt)
# Add errors in assignment examples
aa_err = aa.copy()
aa_erroned = add_errors_in_assignments_proba(aa_err,
model.categories,
pcerrors / 100)
na_err = len(aa_erroned)
# Run the MIP
t1 = time.time()
model2 = MRSort(model.criteria, None, None, None,
model.categories_profiles, None, None, None)
mip = MipMRSort(model2, pt, aa_err)
obj = mip.solve()
ca2_best = obj / na
aa2 = model2.get_assignments(pt)
t_total = time.time() - t1
# Determine the number of erroned alternatives badly assigned
aa2 = model2.pessimist(pt)
ok_errors = ok2_errors = ok = 0
for alt in a:
if aa(alt.id) == aa2(alt.id):
if alt.id in aa_erroned:
ok_errors += 1
ok += 1
if aa_err(alt.id) == aa2(alt.id) and alt.id in aa_erroned:
ok2_errors += 1
total = len(a)
ca2_errors = ok2_errors / total
ca_best = ok / total
ca_errors = ok_errors / total
# Generate alternatives for the generalization
a_gen = generate_alternatives(na_gen)
pt_gen = generate_random_performance_table(a_gen, model.criteria)
aa_gen = model.pessimist(pt_gen)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen = compute_ca(aa_gen, aa_gen2)
aa_gen_err = aa_gen.copy()
aa_gen_erroned = add_errors_in_assignments_proba(aa_gen_err,
model.categories,
pcerrors / 100)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen_err = compute_ca(aa_gen_err, aa_gen2)
# Save all infos in test_result class
t = test_result("%s-%d-%d-%d-%d-%g" % (seed, na, nc, ncat,
na_gen, pcerrors))
model.id = 'initial'
model2.id = 'learned'
pt.id, pt_gen.id = 'learning_set', 'test_set'
aa.id = 'aa'
aa_err.id = 'aa_err'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name),
model, model2, pt, pt_gen, aa, aa_err)
# Input params
t['seed'] = seed
t['na'] = na
t['nc'] = nc
t['ncat'] = ncat
t['na_gen'] = na_gen
t['pcerrors'] = pcerrors
# Ouput params
t['na_err'] = na_err
t['ca_best'] = ca_best
t['ca_errors'] = ca_errors
t['ca2_best'] = ca2_best
t['ca2_errors'] = ca2_errors
t['ca_gen'] = ca_gen
t['ca_gen_err'] = ca_gen_err
t['t_total'] = t_total
return t
def run_test(seed, data, pclearning):
random.seed(seed)
# Separate learning data and test data
pt_learning, pt_test = data.pt.split(2, [pclearning, 100 - pclearning])
aa_learning = data.aa.get_subset(pt_learning.keys())
aa_test = data.aa.get_subset(pt_test.keys())
# Initialize ELECTRE-TRI BM model
cat_profiles = generate_categories_profiles(data.cats)
worst = data.pt.get_worst(data.c)
best = data.pt.get_best(data.c)
b = generate_alternatives(len(data.cats) - 1, 'b')
bpt = None
cvs = None
lbda = None
model = MRSort(data.c, cvs, bpt, lbda, cat_profiles)
# Run the linear program
t1 = time.time()
mip = mip_mrsort(model, pt_learning, aa_learning)
obj = mip.solve()
t_total = time.time() - t1
# CA learning set
aa_learning2 = model.pessimist(pt_learning)
ca_learning = compute_ca(aa_learning, aa_learning2)
auc_learning = model.auc(aa_learning, pt_learning)
diff_learning = compute_confusion_matrix(aa_learning, aa_learning2,
model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2 = model.pessimist(pt_test)
ca_test = compute_ca(aa_test, aa_test2)
auc_test = model.auc(aa_test, pt_test)
diff_test = compute_confusion_matrix(aa_test, aa_test2,
model.categories)
else:
ca_test = 0
auc_test = 0
ncat = len(data.cats)
diff_test = OrderedDict([((a, b), 0) for a in model.categories \
for b in model.categories])
# Compute CA of whole set
aa2 = model.pessimist(data.pt)
ca = compute_ca(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
diff_all = compute_confusion_matrix(data.aa, aa2, model.categories)
t = test_result("%s-%d-%d" % (data.name, seed, pclearning))
model.id = 'learned'
aa_learning.id, aa_test.id = 'learning_set', 'test_set'
pt_learning.id, pt_test.id = 'learning_set', 'test_set'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name),
model, aa_learning, aa_test, pt_learning, pt_test)
t['seed'] = seed
t['na'] = len(data.a)
t['nc'] = len(data.c)
t['ncat'] = len(data.cats)
t['pclearning'] = pclearning
t['na_learning'] = len(aa_learning)
t['na_test'] = len(aa_test)
t['obj'] = obj
t['ca_learning'] = ca_learning
t['ca_test'] = ca_test
t['ca_all'] = ca
t['auc_learning'] = auc_learning
t['auc_test'] = auc_test
t['auc_all'] = auc
for k, v in diff_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in diff_test.items():
t['test_%s_%s' % (k[0], k[1])] = v
for k, v in diff_all.items():
t['all_%s_%s' % (k[0], k[1])] = v
t['t_total'] = t_total
return t
def run_test(seed, data, pclearning, nloop, nmodels, nmeta):
random.seed(seed)
global aaa
global allm
global fct_ca
global LOO
# Separate learning data and test data
if LOO:
pt_learning, pt_test = data.pt.split_LOO(seed)
else:
pt_learning, pt_test = data.pt.split(2, [pclearning, 100 - pclearning])
aa_learning = data.aa.get_subset(pt_learning.keys())
aa_test = data.aa.get_subset(pt_test.keys())
#import pdb; pdb.set_trace()
# Initialize a random model
cat_profiles = generate_categories_profiles(data.cats)
worst = data.pt.get_worst(data.c)
best = data.pt.get_best(data.c)
b = generate_alternatives(len(data.cats) - 1, 'b')
bpt = None
cvs = None
lbda = None
model = MRSort(data.c, cvs, bpt, lbda, cat_profiles)
# if LOO:
# print(data.c, cvs, bpt, lbda, cat_profiles)
# print(model.categories_profiles.to_categories())
# print(model.categories)
# import pdb; pdb.set_trace()
# Run the metaheuristic
t1 = time.time()
pt_sorted = SortedPerformanceTable(pt_learning)
# Algorithm
meta = meta_mrsort(nmodels, model.criteria,
model.categories_profiles.to_categories(),
pt_sorted, aa_learning,
seed = seed * 100)
# if LOO:
# print(nmodels, model.criteria,
# model.categories_profiles.to_categories(),
# pt_sorted, aa_learning)
#import pdb; pdb.set_trace()
#lp_weights = lp_weights,
#heur_profiles = heur_profiles,
#lp_veto_weights = lp_veto_weights,
#heur_veto_profiles = heur_veto_profiles,
for i in range(0, nloop):
model, ca_learning, all_models = meta.optimize(nmeta, fct_ca)
#import pdb; pdb.set_trace()
if ca_learning == 1:
break
t_total = time.time() - t1
aa_learning2 = model.pessimist(pt_learning)
ca_learning = compute_ca(aa_learning, aa_learning2)
ca_learning_good = compute_ca_good(aa_learning, aa_learning2)
#import pdb; pdb.set_trace()
auc_learning = model.auc(aa_learning, pt_learning)
diff_learning = compute_confusion_matrix(aa_learning, aa_learning2,
model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2 = model.pessimist(pt_test)
ca_test = compute_ca(aa_test, aa_test2)
ca_test_good = compute_ca_good(aa_test, aa_test2)
auc_test = model.auc(aa_test, pt_test)
diff_test = compute_confusion_matrix(aa_test, aa_test2,
model.categories)
#import pdb; pdb.set_trace()
else:
ca_test = 0
auc_test = 0
ncat = len(data.cats)
diff_test = OrderedDict([((a, b), 0) for a in model.categories \
for b in model.categories])
# Compute CA of whole set
aa2 = model.pessimist(data.pt)
ca = compute_ca(data.aa, aa2)
ca_good = compute_ca_good(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
diff_all = compute_confusion_matrix(data.aa, aa2, model.categories)
t = test_result("%s-%d-%d-%d-%d-%d" % (data.name, seed, nloop, nmodels,
nmeta, pclearning))
model.id = 'learned'
aa_learning.id, aa_test.id = 'learning_set', 'test_set'
pt_learning.id, pt_test.id = 'learning_set', 'test_set'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name),
model, aa_learning, aa_test, pt_learning, pt_test)
t['seed'] = seed
t['na'] = len(data.a)
t['nc'] = len(data.c)
t['ncat'] = len(data.cats)
t['pclearning'] = pclearning
t['nloop'] = nloop
t['nmodels'] = nmodels
t['nmeta'] = nmeta
t['na_learning'] = len(aa_learning)
t['na_test'] = len(aa_test)
t['ca_learning'] = ca_learning
t['ca_test'] = ca_test
t['ca_all'] = ca
t['ca_learning_good'] = ca_learning_good
t['ca_test_good'] = ca_test_good
t['ca_all_good'] = ca_good
t['auc_learning'] = auc_learning
t['auc_test'] = auc_test
t['auc_all'] = auc
# import pdb; pdb.set_trace()
aaa[seed]=dict()
aaa[seed]['id'] = seed
aaa[seed]['learning_asgmt_id'] = [i.id for i in aa_learning]
aaa[seed]['learning_asgmt'] = [i.category_id for i in aa_learning]
aaa[seed]['learning_asgmt2'] = [i.category_id for i in aa_learning2]
aaa[seed]['test_asgmt_id'] = [i.id for i in aa_test]
aaa[seed]['test_asgmt'] = [i.category_id for i in aa_test]
aaa[seed]['test_asgmt2'] = [i.category_id for i in aa_test2]
aaa[seed]['criteria'] = [i for i,j in model.criteria.items()]
aaa[seed]['criteria_weights'] = [str(i.value) for i in model.cv.values()]
aaa[seed]['profiles_values'] = [str(model.bpt['b1'].performances[i]) for i,j in model.criteria.items()]
aaa[seed]['lambda'] = model.lbda
#[model.bpt['b1'].performances[i] for i,j in model.criteria.items()]
allm[seed]=dict()
allm[seed]['id'] = seed
current_model = 0
allm[seed]['mresults'] = dict()
for all_model in list(all_models)[1:]:
current_model += 1 # skipping the 1rst model already treated
allm[seed]['mresults'][current_model] = ["",""]
aa_learning2_allm = all_model.model.pessimist(pt_learning)
ca_learning_allm = compute_ca(aa_learning, aa_learning2_allm)
ca_learning_good_allm = compute_ca_good(aa_learning, aa_learning2_allm)
auc_learning_allm = all_model.model.auc(aa_learning, pt_learning)
# diff_learning_allm = compute_confusion_matrix(aa_learning, aa_learning2_allm,
# all_model.model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2_allm = all_model.model.pessimist(pt_test)
ca_test_allm = compute_ca(aa_test, aa_test2_allm)
ca_test_good_allm = compute_ca_good(aa_test, aa_test2_allm)
auc_test_allm = all_model.model.auc(aa_test, pt_test)
# diff_test_allm = compute_confusion_matrix(aa_test, aa_test2_allm,
# all_model.categories)
else:
ca_test_allm = 0
auc_test_allm = 0
ncat_allm = len(data.cats)
# diff_test_allm = OrderedDict([((a, b), 0) for a in all_model.categories \
# for b in all_model.model.categories])
# Compute CA of whole set
aa2_allm = all_model.model.pessimist(data.pt)
ca_allm = compute_ca(data.aa, aa2_allm)
ca_good_allm = compute_ca_good(data.aa, aa2_allm)
auc_allm = all_model.model.auc(data.aa, data.pt)
#diff_all_allm = compute_confusion_matrix(data.aa, aa2_allm, all_model.model.categories)
allm[seed]['mresults'][current_model][0] = 'na_learning,na_test,ca_learning,ca_test,ca_all,ca_learning_good,ca_test_good,ca_all_good,auc_learning,auc_test,auc_all'
allm[seed]['mresults'][current_model][1] = str(len(aa_learning)) + "," + str(len(aa_test)) + "," + str(ca_learning_allm) + "," + str(ca_test_allm) + "," + str(ca_allm) + "," + str(ca_learning_good_allm) + "," + str(ca_test_good_allm) + "," + str(ca_good_allm) + "," + str(auc_learning_allm) + "," + str(auc_test_allm) + "," + str(auc_allm)
#allm[seed]['mresults'][current_model][1] =
#all_model.model.bpt['b1'].performances
#all_model.model.cv.values()
#import pdb; pdb.set_trace()
# allm[seed][current_model]['na_learning'] = len(aa_learning)
# allm[seed][current_model]['na_test'] = len(na_test)
# allm[seed][current_model]['ca_learning'] = ca_learning_allm
# allm[seed][current_model]['ca_test'] = ca_test_allm
# allm[seed][current_model]['ca_all'] = ca_allm
# allm[seed][current_model]['ca_learning_good'] = ca_learning_good_allm
# allm[seed][current_model]['ca_test_good'] = ca_test_good_allm
# allm[seed][current_model]['ca_all_good'] = ca_good_allm
# allm[seed][current_model]['auc_learning'] = auc_learning_allm
# allm[seed][current_model]['auc_test'] = auc_test_allm
# allm[seed][current_model]['auc_all'] = auc_allm
for k, v in diff_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in diff_test.items():
t['test_%s_%s' % (k[0], k[1])] = v
for k, v in diff_all.items():
t['all_%s_%s' % (k[0], k[1])] = v
t['t_total'] = t_total
return t
def run_test(seed, data, pclearning, nloop, nmodels, nmeta):
random.seed(seed)
# Separate learning data and test data
pt_learning, pt_test = data.pt.split(2, [pclearning, 100 - pclearning])
aa_learning = data.aa.get_subset(pt_learning.keys())
aa_test = data.aa.get_subset(pt_test.keys())
# Initialize a random model
cat_profiles = generate_categories_profiles(data.cats)
worst = data.pt.get_worst(data.c)
best = data.pt.get_best(data.c)
b = generate_alternatives(len(data.cats) - 1, 'b')
bpt = None
cvs = None
lbda = None
model = MRSort(data.c, cvs, bpt, lbda, cat_profiles)
# Run the metaheuristic
t1 = time.time()
pt_sorted = SortedPerformanceTable(pt_learning)
# Algorithm
meta = meta_mrsort(nmodels,
model.criteria,
model.categories_profiles.to_categories(),
pt_sorted,
aa_learning,
seed=seed * 100)
#lp_weights = lp_weights,
#heur_profiles = heur_profiles,
#lp_veto_weights = lp_veto_weights,
#heur_veto_profiles = heur_veto_profiles,
for i in range(0, nloop):
model, ca_learning = meta.optimize(nmeta)
if ca_learning == 1:
break
t_total = time.time() - t1
aa_learning2 = model.pessimist(pt_learning)
ca_learning = compute_ca(aa_learning, aa_learning2)
auc_learning = model.auc(aa_learning, pt_learning)
diff_learning = compute_confusion_matrix(aa_learning, aa_learning2,
model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2 = model.pessimist(pt_test)
ca_test = compute_ca(aa_test, aa_test2)
auc_test = model.auc(aa_test, pt_test)
diff_test = compute_confusion_matrix(aa_test, aa_test2,
model.categories)
else:
ca_test = 0
auc_test = 0
ncat = len(data.cats)
diff_test = OrderedDict([((a, b), 0) for a in model.categories \
for b in model.categories])
# Compute CA of whole set
aa2 = model.pessimist(data.pt)
ca = compute_ca(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
diff_all = compute_confusion_matrix(data.aa, aa2, model.categories)
t = test_result("%s-%d-%d-%d-%d-%d" %
(data.name, seed, nloop, nmodels, nmeta, pclearning))
model.id = 'learned'
aa_learning.id, aa_test.id = 'learning_set', 'test_set'
pt_learning.id, pt_test.id = 'learning_set', 'test_set'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name), model, aa_learning,
aa_test, pt_learning, pt_test)
t['seed'] = seed
t['na'] = len(data.a)
t['nc'] = len(data.c)
t['ncat'] = len(data.cats)
t['pclearning'] = pclearning
t['nloop'] = nloop
t['nmodels'] = nmodels
t['nmeta'] = nmeta
t['na_learning'] = len(aa_learning)
t['na_test'] = len(aa_test)
t['ca_learning'] = ca_learning
t['ca_test'] = ca_test
t['ca_all'] = ca
t['auc_learning'] = auc_learning
t['auc_test'] = auc_test
t['auc_all'] = auc
for k, v in diff_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in diff_test.items():
t['test_%s_%s' % (k[0], k[1])] = v
for k, v in diff_all.items():
t['all_%s_%s' % (k[0], k[1])] = v
t['t_total'] = t_total
return t
def run_test(seed, data, pclearning, nloop, nmodels, nmeta):
random.seed(seed)
# Separate learning data and test data
pt_learning, pt_test = data.pt.split(2, [pclearning, 100 - pclearning])
aa_learning = data.aa.get_subset(pt_learning.keys())
aa_test = data.aa.get_subset(pt_test.keys())
# Initialize a random model
cat_profiles = generate_categories_profiles(data.cats)
worst = data.pt.get_worst(data.c)
best = data.pt.get_best(data.c)
b = generate_alternatives(len(data.cats) - 1, 'b')
bpt = None
cvs = None
lbda = None
model = MRSort(data.c, cvs, bpt, lbda, cat_profiles)
# Run the metaheuristic
t1 = time.time()
pt_sorted = SortedPerformanceTable(pt_learning)
# Algorithm
meta = MetaMRSortPop3(nmodels, model.criteria,
model.categories_profiles.to_categories(),
pt_sorted, aa_learning,
heur_init_profiles,
lp_weights,
heur_profiles)
for i in range(0, nloop):
model, ca_learning = meta.optimize(nmeta)
t_total = time.time() - t1
aa_learning2 = compute_assignments_majority(meta.models, pt_learning)
ca_learning = compute_ca(aa_learning, aa_learning2)
auc_learning = compute_auc_majority(meta.models, pt_learning)
diff_learning = compute_confusion_matrix(aa_learning, aa_learning2,
model.categories)
# Compute CA of test setting
if len(aa_test) > 0:
aa_test2 = compute_assignments_majority(meta.models, pt_test)
ca_test = compute_ca(aa_test, aa_test2)
auc_test = compute_auc_majority(meta.models, pt_test)
diff_test = compute_confusion_matrix(aa_test, aa_test2,
model.categories)
else:
ca_test = 0
auc_test = 0
ncat = len(data.cats)
diff_test = OrderedDict([((a, b), 0) for a in model.categories \
for b in model.categories])
# Compute CA of whole set
aa2 = compute_assignments_majority(meta.models, data.pt)
ca = compute_ca(data.aa, aa2)
auc = compute_auc_majority(meta.models, data.pt)
diff_all = compute_confusion_matrix(data.aa, aa2, model.categories)
t = test_result("%s-%d-%d-%d-%d-%d" % (data.name, seed, nloop, nmodels,
nmeta, pclearning))
model.id = 'learned'
aa_learning.id, aa_test.id = 'learning_set', 'test_set'
pt_learning.id, pt_test.id = 'learning_set', 'test_set'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name),
aa_learning, aa_test, pt_learning, pt_test, *meta.models)
t['seed'] = seed
t['na'] = len(data.a)
t['nc'] = len(data.c)
t['ncat'] = len(data.cats)
t['pclearning'] = pclearning
t['nloop'] = nloop
t['nmodels'] = nmodels
t['nmeta'] = nmeta
t['na_learning'] = len(aa_learning)
t['na_test'] = len(aa_test)
t['ca_learning'] = ca_learning
t['ca_test'] = ca_test
t['ca_all'] = ca
t['auc_learning'] = auc_learning
t['auc_test'] = auc_test
t['auc_all'] = auc
for k, v in diff_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in diff_test.items():
t['test_%s_%s' % (k[0], k[1])] = v
for k, v in diff_all.items():
t['all_%s_%s' % (k[0], k[1])] = v
t['t_total'] = t_total
return t
def test_mip_mrsort_vc(seed, na, nc, ncat, na_gen, veto_param, pcerrors):
# Generate a random ELECTRE TRI BM model
if vetot == 'binary':
model = generate_random_mrsort_model_with_binary_veto(
nc, ncat, seed, veto_func=veto_func, veto_param=veto_param)
elif vetot == 'coalition':
model = generate_random_mrsort_model_with_coalition_veto(
nc,
ncat,
seed,
veto_weights=indep_veto_weights,
veto_func=veto_func,
veto_param=veto_param)
# Generate a set of alternatives
a = generate_alternatives(na)
pt = generate_random_performance_table(a, model.criteria)
aa = model.pessimist(pt)
nv_m1_learning = sum([model.count_veto_pessimist(ap) for ap in pt])
# Add errors in assignment examples
aa_err = aa.copy()
aa_erroned = add_errors_in_assignments_proba(aa_err, model.categories,
pcerrors / 100)
na_err = len(aa_erroned)
# Run the MIP
t1 = time.time()
model2 = MRSort(model.criteria, None, None, None,
model.categories_profiles, None, None, None)
if algo == MipMRSortVC and vetot == 'binary':
w = {c.id: 1 / len(model.criteria) for c in model.criteria}
w1 = w.keys()[0]
w[w1] += 1 - sum(w.values())
model2.veto_weights = CriteriaValues(
[CriterionValue(c.id, w[c.id]) for c in model.criteria])
model2.veto_lbda = min(w.values())
if algo == MipMRSortVC:
mip = MipMRSortVC(model2, pt, aa, indep_veto_weights)
else:
mip = MipMRSort(model2, pt, aa)
mip.solve()
t_total = time.time() - t1
# Determine the number of erroned alternatives badly assigned
aa2 = model2.pessimist(pt)
nv_m2_learning = sum([model2.count_veto_pessimist(ap) for ap in pt])
cmatrix_learning = compute_confusion_matrix(aa, aa2, model.categories)
ok_errors = ok2_errors = ok = 0
for alt in a:
if aa(alt.id) == aa2(alt.id):
if alt.id in aa_erroned:
ok_errors += 1
ok += 1
if aa_err(alt.id) == aa2(alt.id) and alt.id in aa_erroned:
ok2_errors += 1
total = len(a)
ca2_errors = ok2_errors / total
ca_best = ok / total
ca_errors = ok_errors / total
# Generate alternatives for the generalization
a_gen = generate_alternatives(na_gen)
pt_gen = generate_random_performance_table(a_gen, model.criteria)
aa_gen = model.pessimist(pt_gen)
aa_gen2 = model2.pessimist(pt_gen)
nv_m1_gen = sum([model.count_veto_pessimist(ap) for ap in pt_gen])
nv_m2_gen = sum([model2.count_veto_pessimist(ap) for ap in pt_gen])
if len(aa_gen) > 0:
cmatrix_gen = compute_confusion_matrix(aa_gen, aa_gen2,
model.categories)
ca_gen = compute_ca(aa_gen, aa_gen2)
aa_gen_err = aa_gen.copy()
aa_gen_erroned = add_errors_in_assignments_proba(aa_gen_err,
model.categories,
pcerrors / 100)
aa_gen2 = model2.pessimist(pt_gen)
ca_gen_err = compute_ca(aa_gen_err, aa_gen2)
# Save all infos in test_result class
t = test_result("%s-%d-%d-%d-%d-%s-%d" %
(seed, na, nc, ncat, na_gen, veto_param, pcerrors))
model.id = 'initial'
model2.id = 'learned'
a.id, pt.id = 'learning_set', 'learning_set'
aa.id, aa2.id = 'learning_set_m1', 'learning_set_m2'
a_gen.id, pt_gen.id = 'test_set', 'test_set'
aa_gen.id, aa_gen2.id = 'test_set_m1', 'test_set_m2'
save_to_xmcda("%s/%s.bz2" % (directory, t.test_name), model, model2, a,
a_gen, pt, pt_gen, aa, aa2, aa_gen, aa_gen2)
# Input params
t['seed'] = seed
t['na'] = na
t['nc'] = nc
t['ncat'] = ncat
t['na_gen'] = na_gen
t['veto_param'] = veto_param
t['pcerrors'] = pcerrors
# Ouput params
t['na_err'] = na_err
t['nv_m1_learning'] = nv_m1_learning
t['nv_m2_learning'] = nv_m2_learning
t['nv_m1_gen'] = nv_m1_gen
t['nv_m2_gen'] = nv_m2_gen
t['ca_best'] = ca_best
t['ca_errors'] = ca_errors
t['ca_gen'] = ca_gen
t['ca_gen_err'] = ca_gen_err
t['t_total'] = t_total
for k, v in cmatrix_learning.items():
t['learn_%s_%s' % (k[0], k[1])] = v
for k, v in cmatrix_gen.items():
t['test_%s_%s' % (k[0], k[1])] = v
return t
obj, cvs, cfs, catv = lp.solve(data.aa, data.pt)
model = AVFSort(data.c, cvs, cfs, catv)
elif algo == 'lp_utadis_compat':
model_type = 'utadis'
css = CriteriaValues(CriterionValue(c.id, nseg) for c in data.c)
print("LpAVFSortCompat")
lp = LpAVFSortCompat(data.c, css, data.cats, worst, best)
obj, cvs, cfs, catv = lp.solve(data.aa, data.pt)
model = AVFSort(data.c, cvs, cfs, catv)
else:
print("Invalid algorithm!")
sys.exit(1)
t_total = time.time() - t1
model.id = 'learned'
data.pt.id = 'learning_set'
data.aa.id = 'learning_set'
dt = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
save_to_xmcda("%s/%s-all-%s-%s.bz2" % (DATADIR, algo, data.name, dt), data.aa,
data.pt, model)
aa2 = model.get_assignments(data.pt)
ca = compute_ca(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
anok = []
for a in data.a:
if data.aa[a.id].category_id != aa2[a.id].category_id:
obj, cvs, cfs, catv = lp.solve(data.aa, data.pt)
model = AVFSort(data.c, cvs, cfs, catv)
elif algo == 'lp_utadis_compat':
model_type = 'utadis'
css = CriteriaValues(CriterionValue(c.id, nseg) for c in data.c)
print("LpAVFSortCompat")
lp = LpAVFSortCompat(data.c, css, data.cats, worst, best)
obj, cvs, cfs, catv = lp.solve(data.aa, data.pt)
model = AVFSort(data.c, cvs, cfs, catv)
else:
print("Invalid algorithm!")
sys.exit(1)
t_total = time.time() - t1
model.id = 'learned'
data.pt.id = 'learning_set'
data.aa.id = 'learning_set'
dt = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
save_to_xmcda("%s/%s-all-%s-%s.bz2" % (DATADIR, algo, data.name, dt),
data.aa, data.pt, model)
aa2 = model.get_assignments(data.pt)
ca = compute_ca(data.aa, aa2)
auc = model.auc(data.aa, data.pt)
anok = []
for a in data.a:
if data.aa[a.id].category_id != aa2[a.id].category_id:
